{ "openapi": "3.0.1", "info": { "title": "DCAT / data.json Open-Data Catalog Harvester", "description": "Point at ANY DCAT / Project-Open-Data data.json (energy.gov, NASA, CDC & 100s of gov portals) and harvest every dataset's metadata — title, publisher, contact, accessLevel, landing page, downloads + full distribution[] + raw. Streams even huge feeds. Pay per dataset.", "version": "0.1", "x-build-id": "tTvOieMJdrY9FrJnm" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/datamule~dcat-datajson-harvester/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-datamule-dcat-datajson-harvester", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/datamule~dcat-datajson-harvester/runs": { "post": { "operationId": "runs-sync-datamule-dcat-datajson-harvester", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/datamule~dcat-datajson-harvester/run-sync": { "post": { "operationId": "run-sync-datamule-dcat-datajson-harvester", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "properties": { "dataUrl": { "title": "data.json URL", "type": "string", "description": "The URL of ANY DCAT / Project-Open-Data catalog `data.json`. Every US federal agency (and many state, city and international portals) publishes one. Examples: https://www.energy.gov/data.json, https://data.nasa.gov/data.json, https://data.cdc.gov/data.json. Do NOT use https://catalog.data.gov/data.json — it 404s behind Cloudflare. Leave empty if you use the Agencies picker or a data.json URL list below." }, "dataUrls": { "title": "data.json URLs (multiple)", "type": "array", "description": "Harvest several catalogs in one run — a list of data.json URLs. Combined with the single URL above and the Agencies picker; duplicates are removed. The Max records cap applies across ALL sources together.", "items": { "type": "string" } }, "agencies": { "title": "US federal agencies (built-in registry)", "type": "array", "description": "Convenience shortcut: pick from a small built-in registry of verified US-federal agency catalogs instead of typing URLs. Allowed keys: energy, nasa, cdc, doj, nsf, opm, sba, treasury. (The primary way to use this actor is still the data.json URL field — this registry just saves typing for common agencies.)", "items": { "type": "string" } }, "allAgencies": { "title": "Harvest all built-in agencies", "type": "boolean", "description": "When on, harvest every agency in the built-in registry (energy, nasa, cdc, doj, nsf, opm, sba, treasury). The Max records cap still applies across all of them. Ignored if you provide your own URLs.", "default": false }, "keyword": { "title": "Keyword filter", "type": "string", "description": "Optional case-insensitive keyword. Only datasets whose title, description, identifier, keyword[] or theme[] contain this text are returned. Leave empty to harvest every dataset in the catalog. Example: climate, budget, health." }, "maxRecords": { "title": "Max records (total)", "minimum": 1, "type": "integer", "description": "Maximum total number of datasets to return across all sources (the actor streams the catalog and stops at this cap — it never loads the whole file into memory, so even the 71 MB NASA feed is safe). Each returned dataset is one billable event. Default 25.", "default": 25 }, "bearerToken": { "title": "Bearer token (optional)", "type": "string", "description": "Optional OAuth2 bearer token for a gated catalog. Sent as Authorization: Bearer ***. NOT required for public government catalogs — leave empty. Never logged." }, "extraHeaders": { "title": "Extra request headers", "type": "object", "description": "Optional extra HTTP headers to send with every request, as a JSON object, e.g. {\"Ocp-Apim-Subscription-Key\": \"...\"} for a gated deployment. Leave empty for public catalogs." } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } }